Extracting data from residential leases
Each state's REALTOR association publishes a standard lease, and plenty of landlords write their own, so the same clause sits somewhere different on each. A property manager files one for every tenancy and a lender reads one to verify rental income. Large managers process thousands a year, arriving as e-signed PDFs and phone photographs.
A verifier needs the tenant, the property address, the term and the security deposit. A property management system opens the tenancy from those, and a bank accepts the same lease as proof of where an applicant lives.
What makes residential leases hard
Values typed onto rule lines
A lease prints its blanks as underscores inside sentences, so a value lands mid-clause in bold italic with prose either side.
Terms are chosen by tick
A lease elects between options with checkboxes, so the term or the renewal depends on which box carries a mark.
One clause, several pages
Obligations run across numbered paragraphs on sheet after sheet, each initialed at the foot, with the signatures on the last.
Parse, extract, verify
Parse
Parse turns the document into reading-order Markdown and a hierarchy of blocks (text, tables, figures), and grounds each block to its exact location on the page.
Extract
You define the fields in a JSON schema, and Extract returns their values in a consistent, structured format, each linked back to where it appears in the Markdown.
Verify
Each value links back to where it appears, down to the character range in the Markdown, and the page and bounding box in the source document, so every result can be verified.
One residential lease, end to end
About this document: A completed residential lease on the Arkansas REALTORS® Association's standard form, e-signed through a brokerage. Six portrait pages of numbered clauses, with every value typed on top of the form's own rule lines in bold italic. Page 1 is featured. The tenant's name was replaced before publication, including the typed signature, which was re-set in a handwriting font so it still reads as a signature.
Processing objective: The objective is to find values that were typed into sentences, where a form's blanks sit inside numbered clauses. The address and the deposit are each part of a paragraph of legal prose, and the term was chosen by ticking a box.
Demonstration fields: Property address, Tenant, Lease term, Security deposit
The document
4 of 6 pages
Page 1shown below
Page 2
Page 4
Page 6
Where each value came from
property.address
{
"value": "909 Shall Court Studio Jacksonville AR 72076",
"page": 1,
"range": {
"end": 670,
"start": 473
},
"box": {
"xmin": 0.05401,
"ymin": 0.21693,
"xmax": 0.94615,
"ymax": 0.28367
}
}parties.tenant
{
"value": "Jane Q Sample",
"page": 1,
"range": {
"end": 471,
"start": 178
},
"box": {
"xmin": 0.04472,
"ymin": 0.11286,
"xmax": 0.94654,
"ymax": 0.21316
}
}term.length
{
"value": "12 Months",
"page": 1,
"range": {
"end": 703,
"start": 671
},
"box": {
"xmin": 0.05326,
"ymin": 0.26533,
"xmax": 0.94331,
"ymax": 0.30077
}
}security_deposit
{
"value": 700,
"page": 1,
"range": {
"end": 2357,
"start": 2265
},
"box": {
"xmin": 0.05384,
"ymin": 0.55864,
"xmax": 0.94563,
"ymax": 0.57736
}
}How to try it yourself
Everything on this page is reproducible. The sample, its schema, and the Parse and Extract API outputs are published. You can repeat the same two calls from whichever surface you already build on.
- Claude Skilldescribe the job; the agent writes it
- CLIno code at all
- MCPexpose ADE docs as an agent tool
- REST APIany language
- Pythonlandingai-ade
- TypeScriptlandingai-ade
Documents into data
Accurate
The best accuracy on the difficult documents other tools get wrong, such as messy scans, complicated tables, checkboxes and handwriting.
Auditable
Every answer cites its sources. Values come back with an audit trail (page, bounding box, character range) so a human can review them.
Agentic
Applies multi-step reasoning, and plans before it acts. Handles documents it has never seen before and adapts to variations.
API-first
Composable APIs that drop into any tech stack and can be called from anywhere. Easy to build on and embed in your pipelines and products.
Affordable
Cost-competitive rates with complete price transparency. Spend controls before you run, and every job reports its exact cost.
Enterprise-grade
Built for production and scale from day one. Fully observable and monitored, running securely in our cloud or yours.
Built for high-volume, high-throughput production
- Zero data retention
- Priority rate limits
- Enhanced support
- VPC and on-prem deployment
Available on Team and Enterprise plans.
